Integrated transcriptomic profiling and explainable machine learning to reveal functional reprogramming and biomarker candidates in pancreatic ductal adenocarcinoma.

e16002 Background: Pancreatic ductal adenocarcinoma (PDAC) is among the most aggressive and lethal malignancies of the digestive tract, with a five-year survival rate below 5%. Late diagnosis, high tumour heterogeneity, and limited therapeutic efficacy highlight the urgent need to identify molecular biomarkers and therapeutic targets. This study combines transcriptomic analysis with interpretable machine learning to characterise key functional alterations in PDAC. Methods: Gene expression data from 146 pancreatic tissue samples (72 normal and 74 tumour) were obtained from the Pan-Cancer Atlas (TCGA). Differential expression analysis was performed using DESeq2, followed by functional enrichment analysis via GO and KEGG. A classification model was built using the XGBoost algorithm and evaluated with 500 bootstrapping iterations. Model interpretability was assessed through SHAP (SHapley Additive exPlanations) values to identify genes with the highest predictive contribution, which were then cross-referenced with differentially expressed genes. Results: A comprehensive transcriptomic analysis revealed significant dysregulation of multiple genes between normal and tumor pancreatic tissues. Genes such as GJB3, S100A2, MSLN, and SLC2A1 were notably overexpressed, whereas DEFA6, APOB, and RBP2 exhibited marked downregulation, indicative of impaired exocrine function and aberrant epithelial reprogramming. The XGBoost classification model achieved an average area under the curve (AUC) of 0.9868 and an overall accuracy of 98.6%. SHAP (SHapley Additive exPlanations) analysis identified GJB3, LINC02086, and TSPAN1 as key predictive features. Six genes were concurrently identified as differentially expressed and highly influential within the model, supporting their potential utility as robust biomarkers for pancreatic tumor characterization. Conclusions: Pancreatic ductal adenocarcinoma is marked by extensive transcriptomic reprogramming. The integration of differential gene expression analysis with interpretable machine learning enabled the identification of a molecular signature with potential diagnostic and therapeutic relevance.